timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSWL12c8000s0.0017-seed1 Updated Jul 7
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL12c8000sm0.01-seed1 Updated Jul 7 • 1
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSWL12c8000s0.0004-seed1 Updated Jul 7
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL12c8000sm0.0005-seed1 Updated Jul 8 • 1
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL12c8000sm0.004-seed1 Updated Jul 8 • 1
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL12c8000s0.1-seed1 Updated Jul 7 • 1
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL12c8000sm0.1-seed1 Updated Jul 7 • 2
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSOL12c8000s0.32-seed1 Updated Jul 7
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSOL12c8000sm0.32-seed1 Updated Jul 7
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL2c8000sm1-seed1 Updated Jul 7
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL3c8000s0.01-seed1 Updated Jul 7
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL0c8000sm0.1-seed1 Updated Jul 7
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSOL1c8000s0.01-seed1 Updated Jul 7
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSOL2c8000s0.1-seed1 Updated Jul 7
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSOL3c8000sm1-seed1 Updated Jul 7
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSOL2c8000sm0.01-seed1 Updated Jul 7
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL2c8000sm0.1-seed1 Updated Jul 7
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL3c8000s1-seed1 Updated Jul 7
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL2c8000s0.1-seed1 Updated Jul 7
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL2c8000sm0.01-seed1 Updated Jul 7
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSOL4c8000sm1-seed1 Updated Jul 8
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL12c8000s0.013-seed1 Updated Jul 8
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL12c8000s0.03-seed1 Updated Jul 7
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL12c8000s0.3-seed1 Updated Jul 7
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL12c8000sm0.03-seed1 Updated Jul 7
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL12c8000sm0.3-seed1 Updated Jul 7
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL12c8000s1-seed1 Updated Jul 7
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL12c8000sm1-seed1 Updated Jul 7
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSOL2c8000sm1-seed1 Updated Jul 7
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSRL1c8000s0.1-seed1 Updated Jul 7